Files
llama-carla-merged/tokenizer_config.json

22 lines
522 B
JSON
Raw Normal View History

{
"backend": "tokenizers",
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|eot_id|>",
"is_local": false,
"max_length": 2048,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 131072,
"pad_to_multiple_of": null,
"pad_token": "<|eot_id|>",
"pad_token_type_id": 0,
"padding_side": "left",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first"
}